Adaptive tuning of the sampling domain for dynamic-domain RRTs

Jaillet, Léonard; Yershova, Anna; Valle, S.M. La; Siméon, Thierry

doi:10.1109/iros.2005.1545607

Cited by 95 publications

(75 citation statements)

References 25 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The planners in [13] and [14] also utilize information in the context of PRM to find appropriate sampling strategies for different parts of the configuration space. In contrast to roadmap methods, traditional tree-based methods such as RRT [6], ADDRRT [4], EST [7] rely on limited information, such as distance metrics or simple heuristics to guide the exploration. Although the tree may advance quickly towards its goal, if it gets stuck it becomes more and more difficult to find promising directions for the exploration.…”

Section: Introductionmentioning

confidence: 99%

“…This flexibility tends to prevent the method from getting stuck in the way that other sampling-based tree planners do. Extensive comparisons have been done with RRT [6], a more recent version of RRT called Adaptive Dynamic Domain RRT (ADDRRT) [4], EST [7], and SRT [10] showing that DSLX can be up to two orders of magnitude more efficient. Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discrete Search Leading Continuous Exploration for Kinodynamic Motion Planning

Plaku¹,

Kavraki²,

Vardi

2007

Robotics: Science and Systems III

View full text Add to dashboard Cite

Abstract-This paper presents the Discrete Search Leading continuous eXploration (DSLX) planner, a multi-resolution approach to motion planning that is suitable for challenging problems involving robots with kinodynamic constraints. Initially the method decomposes the workspace to build a graph that encodes the physical adjacency of the decomposed regions. This graph is searched to obtain leads, that is, sequences of regions that can be explored with sampling-based tree methods to generate solution trajectories. Instead of treating the discrete search of the adjacency graph and the exploration of the continuous state space as separate components, DSLX passes information from one to the other in innovative ways. Each lead suggests what regions to explore and the exploration feeds back information to the discrete search to improve the quality of future leads. Information is encoded in edge weights, which indicate the importance of including the regions associated with an edge in the next exploration step. Computation of weights, leads, and the actual exploration make the core loop of the algorithm.Extensive experimentation shows that DSLX is very versatile. The discrete search can drastically change the lead to reflect new information allowing DSLX to find solutions even when sampling-based tree planners get stuck. Experimental results on a variety of challenging kinodynamic motion planning problems show computational speedups of two orders of magnitude over other widely used motion planning methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Discrete Search Leading Continuous Exploration for Kinodynamic Motion Planning

Plaku¹,

Kavraki²,

Vardi

2007

Robotics: Science and Systems III

View full text Add to dashboard Cite

show abstract

“…This parameter is manually selected in our current implementation. However, for more effective performance, an automatic parameter tuning similar to [11] can be implemented.…”

Section: Representing Feasible Configuration Spacesmentioning

confidence: 99%

Motion Planning for Highly Constrained Spaces

Yershova

LaValle

2009

Robot Motion and Control 2009

View full text Add to dashboard Cite

Abstract-We introduce a sampling-based motion planning method that automatically adapts to the difficulties caused by thin regions in the free space (not necessarily narrow corridors). These problems arise frequently in settings such as closed-chain manipulators, humanoid motion planning, and generally any time bodies are in contact or maintain close proximity with each other. Our method combines the aggressive exploration properties of RRTs with the intrinsic dimensionality-reduction properties of kd-trees to focus the sampling and searching in the appropriate subspaces. We handle closed-chains and other kinds of constraints in a general way that avoids inverse kinematics computations, if desired. We have implemented the method and show its computational advantages on a variety of challenging examples.

show abstract

“…The weak probability of such configurations extension is one of the weakness of the RRT method (Jaillet L. et al 2005).…”

Section: Tunning the Rrt Algorithm According To Relations Between Commentioning

confidence: 99%